Python 简单数据提取

学习目标：

提示：简单数据提取

学习内容：

import threading as td
from selenium import webdriver


class MyThread(td.Thread):
    def __init__(self, target, args=()):
        super(MyThread, self).__init__()
        self.target = target
        self.args = args

    def run(self):
        self.result = self.target(*self.args)

    def get_result(self):
        try:
            return self.result
        except:
            return None




def get_url_list(dr):
    dr.implicitly_wait(5)
    try:
        list_data=dr.find_elements_by_xpath('')
        return list_data
    except:
        return "失败"
    finally:
        dr.implicitly_wait(30)


def search(name, delay):
    driver_path = "F:\\个人学习资料\\学习\\爬虫\\chromedriver_win32+(2)\\chromedriver.exe"
    driver = webdriver.Chrome(executable_path=driver_path)
    driver.implicitly_wait(30)
    driver.get('')
    driver.implicitly_wait(30)
    list_data = get_url_list(driver)
#     进行内容页面处理
    check_page_num(driver)


def check_page_num(dr):
    dr.implicitly_wait(20)
    try:
        # 当打开页面为3个的时候，关闭第2个页面
        if (len(dr.window_handles) == 3):
            dr.switch_to.window(dr.window_handles[1])
            dr.close()
        for handle in dr.window_handles:
            dr.switch_to.window(handle)
        data_value = dr.find_element_by_xpath("//table[@id='taskList']/tbody/tr/td[contains(text(),'APF')]/following-sibling::td[3]").text
        return data_value
    except:
        return 0
    finally:
        dr.implicitly_wait(5)
        dr.switch_to.window(dr.window_handles[0])
        dr.implicitly_wait(5)

# 按间距中的绿色按钮以运行脚本。
if __name__ == '__main__':
    t1 = MyThread(search, args=('thread-1', 1))
    t1.start()
    t1.join()
    t1.get_result()